INDEX

Explanations

describing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Rest

-0.28

ä¼ĳæģ¯

-0.28

wash

-0.26

 collectors

-0.25

 Cecil

-0.25

å°Ķæĸ¯

-0.24

 Directorate

-0.24

Ãªt

-0.24

washer

-0.24

æ±Ń

-0.24

POSITIVE LOGITS

gig

0.30

Blank

0.29

Meg

0.27

 blank

0.26

 rise

0.26

 autof

0.26

é«Ģ

0.26

blank

0.26

pon

0.25

Activations Density 0.116%

describing

No Comments

No Known Activations